Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| io.github.firebase/firebase-mcp firebase/firebase-tools Gives AI development tools Firebase-specific capabilities and expertise. | |
| FireCMS Cloud firecmsco/firecms Manage FireCMS Cloud from an AI agent: Firestore data, collections, schemas and users. | |
| firmbase firmbase-be/firmbase-plugin Belgian company data: the CBE register, NBB annual accounts and the Belgian Gazette. | |
| dyslex.ia firou91/dyslex.ia Accessibility MCP server and Agent Skills for AI agents. Requires Superpowers. | |
| io.github.Firrton/defigent firrton/defigent-a2a-protocol Agent messaging inbox (A2A, EIP-712 signed), ERC-8004 directory, status and text hashing for Monad. | |
| FirstKey firstkeyhq/firstkey-mcp FirstKey MCP: agent wallets, free cycles faucet, and one-command site deploys on ICP. | |
| GitHub Dev Tools firstnameapk-design/github-dev-tools GitHub security scanning, code audit, and workflow automation for repositories. | |
| io.github.Firzus/tauri-agent-kit firzus/agent-skills Unofficial Windows WebView2 diagnostics and automation for Tauri 2.12 development builds. | |
| io.github.Firzus/reverse-engineer firzus/agent-skills Read-only reverse engineering of Electron apps, PE/ELF/Mach-O binaries, Go/Rust, .NET and APKs. | |
| TitanStore Commerce MCP fish-tacos/sati-commerce-demo MCP commerce surface for compute credits, API keys, GPU instances, and cloud storage. | |
| io.github.fishcoco-code/guardrly-mcp fishcoco-code/guardrly-mcp Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more | |
| Fusión Studio AI — Branding Tools fision-studio/brand-compass Brand audits, visual catalogs, AI proposals & checkout for LATAM SMBs. Full funnel via MCP. | |
| io.github.fitzyracing1/superuser fitzyracing1/super Permission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit. | |
| Fivebar Trading fivebar-xyz/skills Trading tools for AI agents: token risk checks, swap quotes, unsigned swaps, holdings on 5 chains. | |
| com.fivexer/mcp fivexer/fivexer-platform Route, roster, and track work in a Fivexer workspace from Claude Code and other agentic tools | |
| io.github.FixemBCN/mcp-bifrost fixembcn/mcp-bifrost Delegate bulk code edits to a cheap worker model. Gated, atomic. PHP and Python. | |
| Fixidu fixitindia/fixidu-mcp-server Browse Fixidu live home-services catalog in India - categories, real prices, images. | |
| FixYourDocs fixyourdocs/fixyourdocs File structured docs-feedback reports to the FixYourDocs hub via a file_doc_feedback tool. | |
| Ichimoku Signal fizzl13/ichimoku-signal Free Ichimoku trend; paid confluence, levels, market scan and liquidity-ranked setups via x402. | |
| PlainText Wallet Approval Checker fizzl13/smartcontractexplainer Explains wallet approvals and signature requests in plain language: SAFE, CAUTION or RISK. | |
| x402 Doctor fizzl13/x402-doctor Is this x402/MPP API safe to pay? $0.001 preflight, fixes, a $0.25 test purchase. Free quick check. | |
| PayPal, guarded fizzl13/x402-examples PayPal's Agent Toolkit with limits on refunds and the owner's Approve/Deny above them. | |
| presign-guard wallet fizzl13/x402-examples Agent wallet with limits: pays x402/MPP on Base, Solana, Tempo, XRPL and Algorand; phone approval. | |
| io.github.fjacquet/nano-banana-mcp fjacquet/nano-banana-mcp AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models | |
| FlagQuantum MCP Server flagquantum/mcp-servers Build, compile, run and export FlagQuantum circuits locally. No credentials or outbound network. | |
| io.github.Flan246/dsh-lit-search flan246/dsh-lit-search-mcp Literature search, GB/T 7714/APA citations and BibTeX via Crossref, OpenAlex, Semantic Scholar. | |
| io.github.flatbread-cli/flatbread flatbread-cli/flatbread Share a coding agent's session as one link, secrets redacted first; pull another run's brief. | |
| net.vybit/mcp-server flatirontek/vybit-sdk Push notifications with personalized sounds - manage and trigger your vybits via MCP | |
| Hotel & product prices: Booking.com, Google Hotels, Airbnb, Amazon, eBay flatrow-data-studio/mcp-kits Hotel and product prices: Booking.com, Google Hotels, Expedia, Agoda, Airbnb, Amazon, Walmart, eBay. | |
| Fless Apartment Hunt fless-io/skills Apartment hunting across 13 US states: rents, briefs, hunt links. | |
| Celebrity Jet Tracker (via FlightDB) flightdb/celebrity-jets-mcp Track private jets of celebrities and billionaires: Elon Musk, Taylor Swift, Bezos, Drake and more. | |
| Dictator Alert (via FlightDB) flightdb/dictatoralert-mcp Track government and VIP jets of authoritarian regimes: flight history, airport visits, ADS-B data. | |
| com.boardrepo/boardrepo flintt-dev/boardrepo-plugin Search and review real KiCad and Altium PCB designs: schematics, BOMs, netlists, DRC/ERC. | |
| OpenBoss flisko/openboss-mcp Public internet HP bar. Agents smack it over MCP. They cannot complete payment. | |
| flixconomy.ai: humans and Ari for agents flixconomy/flixconomy-mcp Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR. | |
| QRcodly flob95/qrcodly Create, manage, and share QR codes and short URLs | |
| Flockbay flockbay/flockbay-plugin Build, run and playtest a Godot 4 game in a live Godot editor. Runs inside the Flockbay app. | |
| FLOGVIT.bible flogvit/bible.flogvit.com Read and search the Bible: translations, Hebrew and Greek, study notes, church year and timeline. | |
| affectUI flohoeller/affectui Search, read and install agent-ready React components, screens and blocks for AI products. | |
| io.github.flop-labs/technocore-chat flop-labs/technocore-chat Shared rooms and durable notes for agents over plain HTTP: rendezvous, hand-off, coordination. | |
| KlickyMart floppykit/klickymart Which online stores AI shopping agents can buy from: guest checkout, pay methods, landed cost. | |
| FLORA florafauna-ai/flora-mcp-skills Generate and edit images, video, audio, text and 3D on FLORA's AI creative canvas. | |
| Claude Code Ultimate Guide florianbruniaux/claude-code-ultimate-guide Search the Claude Code Ultimate Guide and machine-readable references from any MCP client. | |
| Spawner flosk6/spawner Preview environments on your self-hosted Spawner server: a copy of your app for each git branch | |
| minitok floticinfo/minitok Verified coding workflows with planning, verification, bounded retries, evidence, and evolution. | |
| com.flo-voice1/acp-sandbox flovoice53-tech/acp-sandbox Agentic Commerce Protocol sandbox: agent builds a cart, human approves a real PayPal payment. | |
| receivemail.dev flovoice53-tech/receivemail-worker Disposable email inboxes for agents and tests: create an address, wait for the email. No signup. | |
| Flow — Base quotes & contract safety for agents flow-executor/flow Best-execution quotes and contract safety checks on Base for AI agents, paid per call via x402. | |
| co.flow2/flow2 flowboard/flow2-mcp Design mobile-first presentations — create, edit, preview, and publish from your AI. | |
| Flowboard flowboardstudio/flowboard Discover cloud shapes and create, inspect, validate, patch, and review architecture diagrams. |
23,051–23,100 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.